tsaol

Create distinctive, production-grade hackathon demo decks with bold design choices that stand out from typical technical presentations. Use when building pitch decks for hackathons, demo days, or competition submissions that need to combine technical depth with visual polish.

Generate card-based architecture diagrams as standalone HTML files. Warm glassmorphism style with CSS-only arrows, rounded cards, and backdrop-filter effects. Use when the user asks to create a pipeline, flow, or architecture diagram in card style.

Full hottrend article pipeline. Aggregates sources, drafts, reviews, refines, generates images, and packages for WeChat publication. 11-step multi-agent workflow.

Quick photo essay pipeline for hot topics. Produces ~600 word image-driven articles using Claude Opus + Kimi K2.5 refinement. 7-step fast workflow.

Plan a series of hottrend articles. Interactive discussion to research topic, propose structure, and generate plan.md. Phase A of the series workflow.

Generate a single article in a hottrend series. Reads plan.md, creates context, runs full hottrend pipeline with series context injection. Phase B of series workflow.

A Stop hook that catches Claude when it claims a UI change is "done", "deployed", or "verified" without showing evidence that a real-browser UI test actually passed. Stops the curl + grep illusion of testing.

Audit an AWS Workshop Studio workshop against content, structure, bilingual, asset, link, and navigation best practices. Generates a structured review report with severity levels and a pass/fail verdict. Use before publishing or after major content changes.

AI skill that compares ML experiment runs across SageMaker MLflow and Training Jobs — surfaces the best model with metrics, cost, and deployment recommendations via natural language.

Generate professional AWS architecture diagrams with official icons using Python's diagrams library, then auto-validate against AWS best practices (bounding box, no crossing lines, color-coded edges, labeled APIs).

Compare ML experiment runs across SageMaker MLflow and Training Jobs — find the best model with metrics, cost, and deployment recommendations.

AI skill that scans AWS data/analytics services (S3, Glue, Athena, Redshift) for security risks, compliance gaps, and operational issues — then provides actionable remediation guidance.

A motivational agent that drives Claude Code to do deeper, more thorough work. Not enforcement — motivation. Changes Claude's identity, injects self-reflection, and raises aspiration levels so agents naturally want to do more. Works through CLAUDE.md directives, hooks, and self-reflection prompts.